What is the 'Neural Link'?

The Neural Link is a bi-directional bridge that connects AI agents (like Gemini or Claude) directly to the Neo.mjs runtime. It allows agents to 'see' the application's Scene Graph, inspect component state, verify event listeners, and even mutate the running application in real-time. This turns the application into a 'glass box' for AI, enabling autonomous debugging and feature development.

Why is Neo.mjs called an 'Application Engine' instead of a framework?

Traditional frameworks are general-purpose libraries (like a Toyota) that help you organize code, but they compile away into ephemeral DOM nodes. Neo.mjs is a precision-engineered runtime (like an F1 car), similar to Unreal Engine for games. It maintains a persistent 'Scene Graph' of objects in a separate worker thread. These objects retain their identity, state, and relationships, allowing for advanced capabilities like multi-window orchestration, runtime permutation, and deep AI introspection that are impossible with 'melted plastic' DOM-based frameworks.

What is 'Context Engineering'?

Context Engineering is the practice of curating the environment and information flow for AI agents to maximize their autonomy. In Neo.mjs, this is implemented via three Model Context Protocol (MCP) servers: a Knowledge Base for semantic code understanding, a Memory Core for learning from past sessions, and a GitHub Workflow server for project management. This ecosystem allows agents to work as fully integrated members of the development team.

What is 'Object Permanence' in the context of Neo.mjs?

In Neo.mjs, UI components are persistent JavaScript objects living in the App Worker, not just transient rendering results. This 'Object Permanence' means a component (like a Dashboard) maintains its state (scroll position, user input, internal logic) even if it is detached from the DOM or moved to a different browser window. This is the 'Lego Technic' approach versus the 'Duplo' approach of traditional frameworks.

What is an 'Agent Operating System'?

Neo.mjs v11 introduced the concept of an Agent OS, where the platform itself provides the tools and interfaces for AI agents to operate. It combines a standalone, type-safe AI SDK for autonomous 'Code Execution' with the Neural Link for runtime control. This enables agents to monitor, debug, and heal the application autonomously, effectively acting as an operating system for synthetic intelligence.

How does Neo.mjs handle multi-window applications?

Neo.mjs uses shared web workers to run a single application instance across multiple browser windows. All windows share the same application state and data in real-time. Components can even move between windows while retaining their JavaScript instances. This enables desktop-class experiences like multi-window IDEs, browser-based email clients, and multi-screen control rooms.

What makes Neo.mjs different from React, Angular, or Vue?

Neo.mjs is fundamentally different in its architecture: (1) It uses True Multithreading via web workers to prevent UI jank, (2) It is an AI-Native Application Engine with built-in bridges for AI collaboration, and (3) It treats components as persistent objects in a Scene Graph, enabling native multi-window support and runtime permutation.

Frontmatter

id	8916
title	Implement Kinetic/Momentum Scrolling in GridDragScroll
state	Closed
labels	enhancementdeveloper-experienceaiperformance
assignees	tobiu
createdAt	Jan 30, 2026, 2:25 PM
updatedAt	Jan 30, 2026, 2:55 PM
githubUrl	https://github.com/neomjs/neo/issues/8916
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 30, 2026, 2:55 PM

Implement Kinetic/Momentum Scrolling in GridDragScroll

Name: Neo.mjs Application Engine
Author: Neo.mjs

Closed v11.24.0 enhancementdeveloper-experienceaiperformance

tobiu commented on Jan 30, 2026, 2:25 PM

Problem: By consolidating touch scrolling into GridDragScroll and using preventDefault() on touchmove events, we have effectively disabled the browser's native momentum (inertial) scrolling. This results in a "dead" feel where the scroll stops instantly upon release, which is jarring for mobile users and sub-optimal for desktop "throw" interactions.

Solution: Implement kinetic scrolling physics within the Neo.main.addon.GridDragScroll addon.

Requirements:

Velocity Tracking: Calculate the velocity (pixels/ms) of the drag gesture based on the last few movement events.
Decay Animation: Upon onDragEnd, if the velocity exceeds a threshold, initiate a requestAnimationFrame loop that continues to scroll the grid.
Friction: Apply a friction factor to the velocity in each frame to gradually slow it down until it stops.
Bounce/Boundary: (Optional but good) Handle hitting the scroll limits gracefully.
Interruption: Ensure that a new mousedown or touchstart instantly stops any active kinetic animation.

Benefits:

Restores the expected "native" feel on mobile devices.
Provides a premium, smooth scrolling experience on desktop (mouse throw).
Maintains the zero-latency architecture while adding polish.

tobiu added the enhancement label on Jan 30, 2026, 2:25 PM

tobiu added the developer-experience label on Jan 30, 2026, 2:25 PM

tobiu added the ai label on Jan 30, 2026, 2:25 PM

tobiu added the performance label on Jan 30, 2026, 2:25 PM

tobiu referenced in commit 9db8eb4 - "feat: Implement Kinetic/Momentum Scrolling in GridDragScroll (#8916)" on Jan 30, 2026, 2:52 PM

tobiu assigned to @tobiu on Jan 30, 2026, 2:54 PM

tobiu Jan 30, 2026, 2:55 PM

Input from Gemini 3 Pro:

✦ I have successfully implemented kinetic (momentum) scrolling in the GridDragScroll addon.

Implementation Details

1. Kinetic Engine (autoScroll):

Decay Animation: Implemented a requestAnimationFrame loop that continues scrolling after the user releases the drag.

Friction: Applies an exponential decay factor of 0.95 per frame to simulate friction.

Threshold: The animation stops automatically when velocity drops below 0.1 pixels/frame.

2. Velocity Tracking:

History Buffer: onDragMove maintains a rolling history of the last 10 drag events (timestamp and position).

Calculation: onDragEnd calculates the release velocity based on the last 100ms of movement data, ensuring the "throw" feels responsive to the user's final gesture.

3. UX Enhancements:

Cursor Feedback: Sets cursor: grabbing !important on document.body during mouse drag operations to provide clear visual feedback.

Interruption: Any new mousedown or touchstart event instantly cancels an active kinetic animation, allowing the user to "catch" and stop the scroll.

Outcome: The grid now supports smooth, physics-based scrolling on both desktop (mouse throw) and mobile (touch momentum), matching the native feel while running entirely on the Main Thread.

tobiu closed this issue on Jan 30, 2026, 2:55 PM